test: Update responses tests based on vllm testing

tests/integration/responses/test_openai_responses.py

@@ -663,6 +663,8 @@ def _skip_service_tier_for_unsupported(self, text_model_id):
             pytest.skip("Azure OpenAI does not support the service_tier parameter")
         if text_model_id.startswith("watsonx/"):
             pytest.skip("WatsonX does not support the service_tier parameter")
+        if text_model_id.startswith("vllm/"):
+            pytest.skip("vLLM does not support the service_tier parameter")
 
     def test_openai_response_with_service_tier_auto(self, openai_client, text_model_id):
         """Test OpenAI response with service_tier='auto'.

tests/integration/responses/test_reasoning.py

@@ -21,7 +21,7 @@ def provider_from_model(client_with_models, text_model_id):
 
 def skip_if_reasoning_content_not_provided(client_with_models, text_model_id):
     provider_type = provider_from_model(client_with_models, text_model_id).provider_type
-    if provider_type in ("remote::openai", "remote::azure", "remote::watsonx"):
+    if provider_type in ("remote::openai", "remote::azure", "remote::watsonx", "remote::vllm"):
         pytest.skip(f"{provider_type} doesn't return reasoning content.")
 
 

tests/integration/responses/test_tool_responses.py

@@ -55,12 +55,13 @@ def test_response_non_streaming_web_search(responses_client, text_model_id, case
         stream=False,
     )
     assert len(response.output) > 1
-    assert response.output[0].type == "web_search_call"
-    assert response.output[0].status == "completed"
-    assert response.output[1].type == "message"
-    assert response.output[1].status == "completed"
-    assert response.output[1].role == "assistant"
-    assert len(response.output[1].content) > 0
+    for output in response.output[:-1]:
+        assert output.type == "web_search_call"
+        assert output.status == "completed"
+    assert response.output[-1].type == "message"
+    assert response.output[-1].status == "completed"
+    assert response.output[-1].role == "assistant"
+    assert len(response.output[-1].content) > 0
     assert_text_contains(response.output_text, case.expected)